skills.rest
mindmorass
mindmorassCOMMUNITY
Explore all skills by this author →
GitHub

github-harvester

Harvest GitHub repository content into a RAG system with authentication.

2|Updated Jan 2, 2026
Search Tags:#documentation#RAG#GitHub#ingestion#issues#code-examples#harvest
One-click install
npx skills add https://github.com/mindmorass/reflex --skill github-harvester
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: github-harvester
Source: https://github.com/mindmorass/reflex/tree/main/plugins/reflex/skills/github-harvester
Command: npx skills add https://github.com/mindmorass/reflex --skill github-harvester

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the extraction and ingestion of GitHub repository content (README files, documentation, code examples, issues, discussions, and releases) to power RAG-enabled search and knowledge bases.

Core Features & Use Cases

  • Readme and documentation extraction to surface project overviews and usage instructions.
  • Code example harvesting to surface runnable snippets for learning or reuse.
  • Issue, discussion, and release harvesting to capture evolving context and changelogs for archival analysis.
  • Use Case: Build a repository knowledge base across multiple projects to accelerate onboarding and engineering search.

Quick Start

Install the required Python packages (PyGithub and httpx) and authenticate with a GitHub token, then run the harvest script against a repo owner/repo to ingest content into your collection.

Frequently Asked Questions about github-harvester

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract GitHub repository content for RAG pipelines?▼

GitHub-harvester automates extraction of README files, documentation, code examples, issues, discussions, and releases from repositories into structured formats ready for RAG ingestion. Install PyGithub and httpx, authenticate with a GitHub token, and run the harvest script against your target repository to ingest content into your collection.

Can I harvest code examples and documentation from multiple GitHub repositories at once?▼

Yes, github-harvester supports configurable scope to ingest content across multiple repositories. It extracts code examples, documentation, and metadata from each repo, enabling you to build a unified knowledge base for accelerated onboarding and engineering search across projects.

What GitHub content does a RAG ingestion tool capture?▼

RAG ingestion tools like github-harvester capture README overviews, documentation files, runnable code examples, issue discussions, release notes, and community discussions. This comprehensive content extraction enables knowledge bases to surface both project context and evolving changelogs for archival analysis.

Do I need authentication to harvest GitHub data for knowledge bases?▼

Yes, github-harvester requires GitHub token authentication to access repository content. This authentication enables configurable scope, chunking, and metadata ingestion across repositories while respecting access permissions and API rate limits.

What's the difference between harvesting GitHub issues and documentation for RAG?▼

Documentation and README files provide static project overviews and usage instructions, while issues and discussions capture evolving context, problem-solving approaches, and community feedback. Harvesting both sources enriches RAG systems with comprehensive knowledge for learning and troubleshooting.

Can github-harvester integrate with existing RAG pipelines?▼

Yes, github-harvester satisfies content extraction, chunking, and metadata ingestion requirements for modular RAG pipelines. Its output formats support integration into downstream indexing and search systems as part of a larger knowledge extraction workflow.

Related Skills

Explore More Data & Analytics Skills→
Nice-Wolf-StudioNice-Wolf-Studio

repository-management

Automate GitHub repository management tasks using the gh CLI.

Official
Advanced
MSamiulHasnatMSamiulHasnat
1

AgentDB Vector Search

Index embeddings and perform context-aware similarity queries for document retrieval.

Community
Advanced
HellblazerHellblazer
4

pdf-processing

Extract text and metadata from PDFs and index them into the nx store.

Community
Advanced
bruno0henriquebruno0henrique

apify

Automate web scraping and data extraction via Apify platform Actors.

Community
Intermediate